LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2503.00493/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTLLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement — mentioned by net01https://news.ycombinator.com/item?id=43299999urn:hackerpapers:mention:2503.00493:43299999Sat, 08 Mar 2025 13:15:47 GMT<p>LLaSE-G1 is a unified speech enhancement model capable of handling multiple tasks without extra task prompts, including: Noise Suppression (SE) Target Speaker Extraction (TSE) Packet Loss Concealment (PLC) Acoustic Echo Cancellation (AEC) Speech Separation (SS) huggingface link: &gt; https://huggingface.co/ASLP-lab/LLaSE-G1 demo page: &gt; https://submission-papers.github.io/LLaSE-G1-demo-page/ arxiv paper: &gt; https://arxiv.org/abs/2503.00493</p><p><a href="https://hackerpaper.kaipfister.de/p/2503.00493/">Paper and discussion history</a>. A mention is not an endorsement.</p>eess.AS